Easy to use Audio Tagging in PyTorch

Last update: Dec 22, 2022

Overview

Audio Classification, Tagging & Sound Event Detection in PyTorch

Progress:

Model Zoo

AudioSet Pretrained Models

Model	Task	mAP ^(%)	Sample Rate ^(kHz)	Window Length	Num Mels	Fmax	Weights
CNN14	Tagging	43.1	32	1024	64	14k	download
CNN14_16k	Tagging	43.8	16	512	64	8k	download

CNN14_DecisionLevelMax	SED	38.5	32	1024	64	14k	download

Note: These models will be used as a pretrained model in the fine-tuning tasks below. Check out audioset-tagging-cnn, if you want to train on AudioSet dataset.

Fine-tuned Classification Models

Model	Dataset	Accuracy ^(%)	Sample Rate ^(kHz)	Weights
CNN14	ESC50 (Fold-5)	95.75	32	download
CNN14	FSDKaggle2018 (test)	93.56	32	download
CNN14	SpeechCommandsv1 (val/test)	96.60/96.77	32	download

Fine-tuned Tagging Models

Model	Dataset	mAP(%)	AUC	d-prime	Sample Rate ^(kHz)	Config	Weights
CNN14	FSDKaggle2019	-	-	-	32	-	-

Fine-tuned SED Models

Model	Dataset	F1	Sample Rate ^(kHz)	Config	Weights
CNN14_DecisionLevelMax	DESED	-	32	-	-

Supported Datasets

Dataset	Task	Classes	Train	Val	Test	Audio Length	Audio Spec	Size
ESC-50	Classification	50	2,000	5 folds	-	5s	44.1kHz, mono	600MB
UrbanSound8k	Classification	10	8,732	10 folds	-	<=4s	Vary	5.6GB
FSDKaggle2018	Classification	41	9,473	-	1,600	300ms~30s	44.1kHz, mono	4.6GB
SpeechCommandsv1	Classification	30	51,088	6,798	6,835	<=1s	16kHz, mono	1.4GB
SpeechCommandsv2	Classification	35	84,843	9,981	11,005	<=1s	16kHz, mono	2.3GB

FSDKaggle2019*	Tagging	80	4,970+19,815	-	4,481	300ms~30s	44.1kHz, mono	24GB
MTT*	Tagging	50	19,000	-	-	-	-	3GB

DESED*	SED	10	-	-	-	10	-	-

Notes: * datasets are not available yet. Classification dataset are treated as multi-class/single-label classification and tagging and sed datasets are treated as multi-label classification.

Dataset Structure (click to expand)

Download the dataset and prepare it into the following structure.

datasets
|__ ESC50
    |__ audio

|__ Urbansound8k
    |__ audio

|__ FSDKaggle2018
    |__ audio_train
    |__ audio_test
    |__ FSDKaggle2018.meta
        |__ train_post_competition.csv
        |__ test_post_competition_scoring_clips.csv

|__ SpeechCommandsv1/v2
    |__ bed
    |__ bird
    |__ ...
    |__ testing_list.txt
    |__ validation_list.txt

Augmentations (click to expand)

Currently, the following augmentations are supported. More will be added in the future. You can test the effects of augmentations with this notebook

WaveForm Augmentations:

Spectrogram Augmentations:

Time Masking
Frequency Masking
Filter Augmentation

Usage

Requirements (click to expand)

python >= 3.6
pytorch >= 1.8.1
torchaudio >= 0.8.1

Other requirements can be installed with pip install -r requirements.txt.

Configuration (click to expand)

Create a configuration file in configs. Sample configuration for ESC50 dataset can be found here.
Copy the contents of this and then edit the fields you think if it is needed.
This configuration file is needed for all of training, evaluation and prediction scripts.

Training (click to expand)

To train with a single GPU:

$ python tools/train.py --cfg configs/CONFIG_FILE_NAME.yaml

To train with multiple gpus, set DDP field in config file to true and run as follows:

$ python -m torch.distributed.launch --nproc_per_node=2 --use_env tools/train.py --cfg configs/CONFIG_FILE_NAME.yaml

Evaluation (click to expand)

Make sure to set MODEL_PATH of the configuration file to your trained model directory.

$ python tools/val.py --cfg configs/CONFIG_FILE.yaml

Audio Classification/Tagging Inference

Set MODEL_PATH of the configuration file to your model's trained weights.
Change the dataset name in DATASET >> NAME as your trained model's dataset.
Set the testing audio file path in TEST >> FILE.
Run the following command.

$ python tools/infer.py --cfg configs/CONFIG_FILE.yaml

## for example
$ python tools/infer.py --cfg configs/audioset.yaml

You will get an output similar to this:

Class                     Confidence
----------------------  ------------
Speech                     0.897762
Telephone bell ringing     0.752206
Telephone                  0.219329
Inside, small room         0.20761
Music                      0.0770325

Sound Event Detection Inference

Set MODEL_PATH of the configuration file to your model's trained weights.
Change the dataset name in DATASET >> NAME as your trained model's dataset.
Set the testing audio file path in TEST >> FILE.
Run the following command.

$ python tools/sed_infer.py --cfg configs/CONFIG_FILE.yaml

## for example
$ python tools/sed_infer.py --cfg configs/audioset_sed.yaml

You will get an output similar to this:

Class                     Start    End
----------------------  -------  -----
Speech                      2.2    7
Telephone bell ringing      0      2.5

The following plot will also be shown, if you set PLOT to true:

References (click to expand)

Citations (click to expand)

@misc{kong2020panns,
      title={PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition}, 
      author={Qiuqiang Kong and Yin Cao and Turab Iqbal and Yuxuan Wang and Wenwu Wang and Mark D. Plumbley},
      year={2020},
      eprint={1912.10211},
      archivePrefix={arXiv},
      primaryClass={cs.SD}
}

@misc{gong2021ast,
      title={AST: Audio Spectrogram Transformer}, 
      author={Yuan Gong and Yu-An Chung and James Glass},
      year={2021},
      eprint={2104.01778},
      archivePrefix={arXiv},
      primaryClass={cs.SD}
}

@misc{nam2021heavily,
      title={Heavily Augmented Sound Event Detection utilizing Weak Predictions}, 
      author={Hyeonuk Nam and Byeong-Yun Ko and Gyeong-Tae Lee and Seong-Hu Kim and Won-Ho Jung and Sang-Min Choi and Yong-Hwa Park},
      year={2021},
      eprint={2107.03649},
      archivePrefix={arXiv},
      primaryClass={eess.AS}
}

You might also like...

TorchMetrics is a collection of 25+ PyTorch metrics implementations and an easy-to-use API to create custom metrics.

Machine learning metrics for distributed, scalable PyTorch applications.

1.2k Jan 6, 2023

TorchFlare is a simple, beginner-friendly, and easy-to-use PyTorch Framework train your models effortlessly.

TorchFlare TorchFlare is a simple, beginner-friendly and an easy-to-use PyTorch Framework train your models without much effort. It provides an almost

85 Dec 26, 2022

A more easy-to-use implementation of KPConv based on PyTorch.

A more easy-to-use implementation of KPConv This repo contains a more easy-to-use implementation of KPConv based on PyTorch. Introduction KPConv is a

36 Dec 29, 2022

Use MATLAB to simulate the signal and extract features. Use PyTorch to build and train deep network to do spectrum sensing.

Deep-Learning-based-Spectrum-Sensing Use MATLAB to simulate the signal and extract features. Use PyTorch to build and train deep network to do spectru

10 Dec 14, 2022

Fast image augmentation library and easy to use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about library: https://www.mdpi.com/2078-2489/11/2/125

Albumentations Albumentations is a Python library for image augmentation. Image augmentation is used in deep learning and computer vision tasks to inc

11.4k Jan 9, 2023

Fast, flexible and easy to use probabilistic modelling in Python.

Please consider citing the JMLR-MLOSS Manuscript if you've used pomegranate in your academic work! pomegranate is a package for building probabilistic

3k Dec 29, 2022

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

What is xLearn? xLearn is a high performance, easy-to-use, and scalable machine learning package that contains linear model (LR), factorization machin

3k Jan 3, 2023

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

What is xLearn? xLearn is a high performance, easy-to-use, and scalable machine learning package that contains linear model (LR), factorization machin

2.8k Feb 12, 2021

A fast and easy to use, moddable, Python based Minecraft server!

PyMine PyMine - The fastest, easiest to use, Python-based Minecraft Server! Features Note: This list is not always up to date, and doesn't contain all

144 Dec 30, 2022

Releases(v0.2.0)

v0.2.0(Aug 17, 2021)
This release includes the following:

Fine-tuned on ESC50, FSDKaggle2018, SpeechCommandsv1

Add waveform augmentations

Add spectrogram augmentations

Add augmentation testing notebook

Add tagging metrics

Source code(tar.gz)
Source code(zip)
v0.1.0(Aug 13, 2021)
Add the following datasets:

ESC50

UrbanSound8k

FSDKaggle2018

SpeechCommandsv1/v2

Release fine-tuned model on ESC50.
Source code(tar.gz)
Source code(zip)

Owner

sithu3

AI Developer

GitHub Repository

TransPrompt - Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification

TransPrompt This code is implement for our EMNLP 2021's paper 《TransPrompt：Towards an Automatic Transferable Prompting Framework for Few-shot Text Cla

23 Dec 21, 2022

We will release the code of "ConTNet: Why not use convolution and transformer at the same time?" in this repo

ConTNet Introduction ConTNet (Convlution-Tranformer Network) is proposed mainly in response to the following two issues: (1) ConvNets lack a large rec

93 Nov 08, 2022

ESGD-M - A stochastic non-convex second order optimizer, suitable for training deep learning models, for PyTorch

53 Dec 29, 2022

3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces (ICCV 2021)

3DIAS_Pytorch This repository contains the official code to reproduce the results from the paper: 3DIAS: 3D Shape Reconstruction with Implicit Algebra

21 Dec 12, 2022

Optimizing synthesizer parameters using gradient approximation

Optimizing synthesizer parameters using gradient approximation NASH 2021 Hackathon! These are some experiments I conducted during NASH 2021, the Neura

10 Feb 10, 2022

The source code for 'Noisy-Labeled NER with Confidence Estimation' accepted by NAACL 2021

Kun Liu*, Yao Fu*, Chuanqi Tan, Mosha Chen, Ningyu Zhang, Songfang Huang, Sheng Gao. Noisy-Labeled NER with Confidence Estimation. NAACL 2021. [arxiv]

30 Nov 12, 2022

The implementation of FOLD-R++ algorithm

FOLD-R-PP The implementation of FOLD-R++ algorithm. The target of FOLD-R++ algorithm is to learn an answer set program for a classification task. Inst

13 Dec 23, 2022

Code and real data for the paper "Counterfactual Temporal Point Processes", available at arXiv.

counterfactual-tpp This is a repository containing code and real data for the paper Counterfactual Temporal Point Processes. Pre-requisites This code

11 Dec 09, 2022

Deep Learning Models for Causal Inference

Extensive tutorials for learning how to build deep learning models for causal inference using selection on observables in Tensorflow 2.

151 Dec 31, 2022

Harmonic Memory Networks for Graph Completion

HMemNetworks Code and documentation for Harmonic Memory Networks, a series of models for compositionally assembling representations of graph elements

0 Oct 27, 2021

Interpretable-contrastive-word-mover-s-embedding

Interpretable-contrastive-word-mover-s-embedding Paper Datasets Here is a Dropbox link to the datasets used in the paper: https://www.dropbox.com/sh/n

0 Nov 02, 2021

PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation (TPAMI).

PFENet This is the implementation of our paper PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation that has been accepted to IEE

230 Dec 31, 2022

Pytorch implementation for "Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets" (ECCV 2020 Spotlight)

Distribution-Balanced Loss [Paper] The implementation of our paper Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets (

304 Dec 22, 2022

Easy to use Audio Tagging in PyTorch

Related tags

Overview

Audio Classification, Tagging & Sound Event Detection in PyTorch

Model Zoo

Supported Datasets

Usage

You might also like...

TorchMetrics is a collection of 25+ PyTorch metrics implementations and an easy-to-use API to create custom metrics.

TorchFlare is a simple, beginner-friendly, and easy-to-use PyTorch Framework train your models effortlessly.

A more easy-to-use implementation of KPConv based on PyTorch.

Use MATLAB to simulate the signal and extract features. Use PyTorch to build and train deep network to do spectrum sensing.

Fast image augmentation library and easy to use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about library: https://www.mdpi.com/2078-2489/11/2/125

Fast, flexible and easy to use probabilistic modelling in Python.

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

A fast and easy to use, moddable, Python based Minecraft server!

Releases(v0.2.0)

v0.2.0(Aug 17, 2021)

v0.1.0(Aug 13, 2021)

Owner

sithu3

TransPrompt - Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification

We will release the code of "ConTNet: Why not use convolution and transformer at the same time?" in this repo

ESGD-M - A stochastic non-convex second order optimizer, suitable for training deep learning models, for PyTorch

3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces (ICCV 2021)

Optimizing synthesizer parameters using gradient approximation

The source code for 'Noisy-Labeled NER with Confidence Estimation' accepted by NAACL 2021

The implementation of FOLD-R++ algorithm

Code and real data for the paper "Counterfactual Temporal Point Processes", available at arXiv.

Deep Learning Models for Causal Inference

Harmonic Memory Networks for Graph Completion

Interpretable-contrastive-word-mover-s-embedding

PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation (TPAMI).

Pytorch implementation for "Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets" (ECCV 2020 Spotlight)

Towards Implicit Text-Guided 3D Shape Generation (CVPR2022)

Provide baselines and evaluation metrics of the task: traffic flow prediction

Official Repsoitory for "Activate or Not: Learning Customized Activation." [CVPR 2021]

PyTorch Implementation of Temporal Output Discrepancy for Active Learning, ICCV 2021

Current state of supervised and unsupervised depth completion methods

MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition

Code for Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing(ICCV21)